kotovalexarian-likes-github/ruby--ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
Code Releases Activity

* ext/nkf/nkf-utf8.c: Update nkf.c rev:1.157.

Browse source 
* ext/nkf/nkf.c (rb_nkf_enc_get): replicate proper based encoding.

* ext/nkf/kconv.c (Kconv#kconv, to*): use self.encoding as from_enc
  when from_enc isn't given.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@14481 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
naruse 2007-12-22 08:36:30 +00:00
parent eff45d2cc8
commit 573bd7500b
4 changed files with 149 additions and 165 deletions
Download patch file Download diff file Expand all files Collapse all files

9
ChangeLog
View file

@ -1,3 +1,12 @@
Sat Dec 22 17:35:59 2007 NARUSE, Yui <naruse@ruby-lang.org>
* ext/nkf/nkf-utf8.c: Update nkf.c rev:1.157.
* ext/nkf/nkf.c (rb_nkf_enc_get): replicate proper based encoding.
* ext/nkf/kconv.c (Kconv#kconv, to*): use self.encoding as from_enc
when from_enc isn't given.
Sat Dec 22 17:31:41 2007 NAKAMURA Usaku <usa@ruby-lang.org> Sat Dec 22 17:31:41 2007 NAKAMURA Usaku <usa@ruby-lang.org>
* lib/mkmf.rb ($extmk): fixed broken condition. * lib/mkmf.rb ($extmk): fixed broken condition.

78
ext/nkf/lib/kconv.rb
View file

@ -85,11 +85,6 @@ module Kconv
# #
# Convert <code>str</code> to out_code. # Convert <code>str</code> to out_code.
# <code>out_code</code> and <code>in_code</code> are given as constants of Kconv. # <code>out_code</code> and <code>in_code</code> are given as constants of Kconv.
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want to decode them, use NKF.nkf.
def kconv(str, to_enc, from_enc=nil) def kconv(str, to_enc, from_enc=nil)
opt = '' opt = ''
opt += ' --ic=' + from_enc.name if from_enc opt += ' --ic=' + from_enc.name if from_enc
@ -107,13 +102,8 @@ module Kconv
# Kconv.tojis(str) -> string # Kconv.tojis(str) -> string
# #
# Convert <code>str</code> to ISO-2022-JP # Convert <code>str</code> to ISO-2022-JP
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-jxm0', str).
def tojis(str) def tojis(str)
::NKF::nkf('-jm', str) kconv(str, JIS)
end end
module_function :tojis module_function :tojis
@ -121,13 +111,8 @@ module Kconv
# Kconv.toeuc(str) -> string # Kconv.toeuc(str) -> string
# #
# Convert <code>str</code> to EUC-JP # Convert <code>str</code> to EUC-JP
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-exm0', str).
def toeuc(str) def toeuc(str)
::NKF::nkf('-em', str) kconv(str, EUC)
end end
module_function :toeuc module_function :toeuc
@ -135,13 +120,8 @@ module Kconv
# Kconv.tosjis(str) -> string # Kconv.tosjis(str) -> string
# #
# Convert <code>str</code> to Shift_JIS # Convert <code>str</code> to Shift_JIS
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-sxm0', str).
def tosjis(str) def tosjis(str)
::NKF::nkf('-sm', str) kconv(str, SJIS)
end end
module_function :tosjis module_function :tosjis
@ -149,13 +129,8 @@ module Kconv
# Kconv.toutf8(str) -> string # Kconv.toutf8(str) -> string
# #
# Convert <code>str</code> to UTF-8 # Convert <code>str</code> to UTF-8
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-wxm0', str).
def toutf8(str) def toutf8(str)
::NKF::nkf('-wm', str) kconv(str, UTF8)
end end
module_function :toutf8 module_function :toutf8
@ -163,13 +138,8 @@ module Kconv
# Kconv.toutf16(str) -> string # Kconv.toutf16(str) -> string
# #
# Convert <code>str</code> to UTF-16 # Convert <code>str</code> to UTF-16
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-w16xm0', str).
def toutf16(str) def toutf16(str)
::NKF::nkf('-w16m', str) kconv(str, UTF16)
end end
module_function :toutf16 module_function :toutf16
@ -177,13 +147,8 @@ module Kconv
# Kconv.toutf32(str) -> string # Kconv.toutf32(str) -> string
# #
# Convert <code>str</code> to UTF-32 # Convert <code>str</code> to UTF-32
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-w32xm0', str).
def toutf32(str) def toutf32(str)
::NKF::nkf('-w32m', str) kconv(str, UTF32)
end end
module_function :toutf32 module_function :toutf32
@ -251,6 +216,7 @@ class String
# convert halfwidth katakana to fullwidth katakana. # convert halfwidth katakana to fullwidth katakana.
# If you don't want to decode them, use NKF.nkf. # If you don't want to decode them, use NKF.nkf.
def kconv(to_enc, from_enc=nil) def kconv(to_enc, from_enc=nil)
form_enc = self.encoding.name if !from_enc && self.encoding != Encoding.list[0]
Kconv::kconv(self, to_enc, from_enc) Kconv::kconv(self, to_enc, from_enc)
end end
@ -262,66 +228,36 @@ class String
# String#tojis -> string # String#tojis -> string
# #
# Convert <code>self</code> to ISO-2022-JP # Convert <code>self</code> to ISO-2022-JP
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-jxm0', str).
def tojis; Kconv.tojis(self) end def tojis; Kconv.tojis(self) end
# call-seq: # call-seq:
# String#toeuc -> string # String#toeuc -> string
# #
# Convert <code>self</code> to EUC-JP # Convert <code>self</code> to EUC-JP
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-exm0', str).
def toeuc; Kconv.toeuc(self) end def toeuc; Kconv.toeuc(self) end
# call-seq: # call-seq:
# String#tosjis -> string # String#tosjis -> string
# #
# Convert <code>self</code> to Shift_JIS # Convert <code>self</code> to Shift_JIS
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-sxm0', str).
def tosjis; Kconv.tosjis(self) end def tosjis; Kconv.tosjis(self) end
# call-seq: # call-seq:
# String#toutf8 -> string # String#toutf8 -> string
# #
# Convert <code>self</code> to UTF-8 # Convert <code>self</code> to UTF-8
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-wxm0', str).
def toutf8; Kconv.toutf8(self) end def toutf8; Kconv.toutf8(self) end
# call-seq: # call-seq:
# String#toutf16 -> string # String#toutf16 -> string
# #
# Convert <code>self</code> to UTF-16 # Convert <code>self</code> to UTF-16
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-w16xm0', str).
def toutf16; Kconv.toutf16(self) end def toutf16; Kconv.toutf16(self) end
# call-seq: # call-seq:
# String#toutf32 -> string # String#toutf32 -> string
# #
# Convert <code>self</code> to UTF-32 # Convert <code>self</code> to UTF-32
#
# *Note*
# This method decode MIME encoded string and
# convert halfwidth katakana to fullwidth katakana.
# If you don't want it, use NKF.nkf('-w32xm0', str).
def toutf32; Kconv.toutf32(self) end def toutf32; Kconv.toutf32(self) end
# #

211
ext/nkf/nkf-utf8/nkf.c
View file

@ -32,7 +32,7 @@
***********************************************************************/ ***********************************************************************/
/* $Id$ */ /* $Id$ */
#define NKF_VERSION "2.0.8" #define NKF_VERSION "2.0.8"
#define NKF_RELEASE_DATE "2007-12-19" #define NKF_RELEASE_DATE "2007-12-22"
#define COPY_RIGHT \ #define COPY_RIGHT \
"Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa),2000 S. Kono, COW\n" \ "Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa),2000 S. Kono, COW\n" \
"Copyright (C) 2002-2007 Kono, Furukawa, Naruse, mastodon" "Copyright (C) 2002-2007 Kono, Furukawa, Naruse, mastodon"
@ -228,8 +228,6 @@ void djgpp_setbinmode(FILE *fp)
enum nkf_encodings { enum nkf_encodings {
ASCII, ASCII,
JIS_X_0208,
JIS_X_0201,
ISO_8859_1, ISO_8859_1,
ISO_2022_JP, ISO_2022_JP,
CP50220, CP50220,
@ -262,52 +260,84 @@ enum nkf_encodings {
UTF_32BE_BOM, UTF_32BE_BOM,
UTF_32LE, UTF_32LE,
UTF_32LE_BOM, UTF_32LE_BOM,
JIS_X_0212=0x2844, JIS_X_0201=0x1000,
JIS_X_0213_1=0x284F, JIS_X_0208,
JIS_X_0213_2=0x2850, JIS_X_0212,
JIS_X_0213_1,
JIS_X_0213_2,
BINARY BINARY
}; };
static const struct {
const int id; nkf_char s_iconv(nkf_char c2, nkf_char c1, nkf_char c0);
const char *name; nkf_char e_iconv(nkf_char c2, nkf_char c1, nkf_char c0);
} encoding_id_to_name_table[] = { nkf_char w_iconv(nkf_char c2, nkf_char c1, nkf_char c0);
{ASCII, "ASCII"}, nkf_char w_iconv16(nkf_char c2, nkf_char c1, nkf_char c0);
{ISO_8859_1, "ISO-8859-1"}, nkf_char w_iconv32(nkf_char c2, nkf_char c1, nkf_char c0);
{ISO_2022_JP, "ISO-2022-JP"}, void j_oconv(nkf_char c2, nkf_char c1);
{CP50220, "CP50220"}, void s_oconv(nkf_char c2, nkf_char c1);
{CP50221, "CP50221"}, void e_oconv(nkf_char c2, nkf_char c1);
{CP50222, "CP50222"}, void w_oconv(nkf_char c2, nkf_char c1);
{ISO_2022_JP_1, "ISO-2022-JP-1"}, void w_oconv16(nkf_char c2, nkf_char c1);
{ISO_2022_JP_3, "ISO-2022-JP-3"}, void w_oconv32(nkf_char c2, nkf_char c1);
{SHIFT_JIS, "Shift_JIS"},
{WINDOWS_31J, "WINDOWS-31J"}, typedef struct {
{CP10001, "CP10001"}, char *name;
{EUC_JP, "EUC-JP"}, nkf_char (*iconv_func)(nkf_char c2, nkf_char c1, nkf_char c0);
{CP51932, "CP51932"}, void (*oconv_func)(nkf_char c2, nkf_char c1);
{EUCJP_MS, "eucJP-MS"}, } nkf_native_encoding;
{EUCJP_ASCII, "eucJP-ASCII"},
{SHIFT_JISX0213, "Shift_JISX0213"}, nkf_native_encoding NkfEncodingASCII = { "US_ASCII", e_iconv, e_oconv };
{SHIFT_JIS_2004, "Shift_JIS-2004"}, nkf_native_encoding NkfEncodingISO_2022_JP = { "ISO-2022-JP", e_iconv, j_oconv };
{EUC_JISX0213, "EUC-JISX0213"}, nkf_native_encoding NkfEncodingShift_JIS = { "Shift_JIS", s_iconv, s_oconv };
{EUC_JIS_2004, "EUC-JIS-2004"}, nkf_native_encoding NkfEncodingEUC_JP = { "EUC-JP", e_iconv, e_oconv };
{UTF_8, "UTF-8"}, nkf_native_encoding NkfEncodingUTF_8 = { "UTF-8", w_iconv, w_oconv };
{UTF_8N, "UTF-8N"}, nkf_native_encoding NkfEncodingUTF_16 = { "UTF-16", w_iconv16, w_oconv16 };
{UTF_8_BOM, "UTF-8-BOM"}, nkf_native_encoding NkfEncodingUTF_32 = { "UTF-32", w_iconv32, w_oconv32 };
{UTF8_MAC, "UTF8-MAC"},
{UTF_16, "UTF-16"}, typedef struct {
{UTF_16BE, "UTF-16BE"}, int id;
{UTF_16BE_BOM, "UTF-16BE-BOM"}, char *name;
{UTF_16LE, "UTF-16LE"}, nkf_native_encoding *based_encoding;
{UTF_16LE_BOM, "UTF-16LE-BOM"}, } nkf_encoding;
{UTF_32, "UTF-32"}, nkf_encoding nkf_encoding_table[] = {
{UTF_32BE, "UTF-32BE"}, {ASCII, "ASCII", &NkfEncodingASCII},
{UTF_32BE_BOM, "UTF-32BE-BOM"}, {ISO_8859_1, "ISO-8859-1", &NkfEncodingASCII},
{UTF_32LE, "UTF-32LE"}, {ISO_2022_JP, "ISO-2022-JP", &NkfEncodingASCII},
{UTF_32LE_BOM, "UTF-32LE-BOM"}, {CP50220, "CP50220", &NkfEncodingISO_2022_JP},
{BINARY, "BINARY"}, {CP50221, "CP50221", &NkfEncodingISO_2022_JP},
{-1, ""} {CP50222, "CP50222", &NkfEncodingISO_2022_JP},
{ISO_2022_JP_1, "ISO-2022-JP-1", &NkfEncodingISO_2022_JP},
{ISO_2022_JP_3, "ISO-2022-JP-3", &NkfEncodingISO_2022_JP},
{SHIFT_JIS, "Shift_JIS", &NkfEncodingShift_JIS},
{WINDOWS_31J, "WINDOWS-31J", &NkfEncodingShift_JIS},
{CP10001, "CP10001", &NkfEncodingShift_JIS},
{EUC_JP, "EUC-JP", &NkfEncodingEUC_JP},
{CP51932, "CP51932", &NkfEncodingEUC_JP},
{EUCJP_MS, "eucJP-MS", &NkfEncodingEUC_JP},
{EUCJP_ASCII, "eucJP-ASCII", &NkfEncodingEUC_JP},
{SHIFT_JISX0213, "Shift_JISX0213", &NkfEncodingShift_JIS},
{SHIFT_JIS_2004, "Shift_JIS-2004", &NkfEncodingShift_JIS},
{EUC_JISX0213, "EUC-JISX0213", &NkfEncodingEUC_JP},
{EUC_JIS_2004, "EUC-JIS-2004", &NkfEncodingEUC_JP},
{UTF_8, "UTF-8", &NkfEncodingUTF_8},
{UTF_8N, "UTF-8N", &NkfEncodingUTF_8},
{UTF_8_BOM, "UTF-8-BOM", &NkfEncodingUTF_8},
{UTF8_MAC, "UTF8-MAC", &NkfEncodingUTF_8},
{UTF_16, "UTF-16", &NkfEncodingUTF_16},
{UTF_16BE, "UTF-16BE", &NkfEncodingUTF_16},
{UTF_16BE_BOM, "UTF-16BE-BOM", &NkfEncodingUTF_16},
{UTF_16LE, "UTF-16LE", &NkfEncodingUTF_16},
{UTF_16LE_BOM, "UTF-16LE-BOM", &NkfEncodingUTF_16},
{UTF_32, "UTF-32", &NkfEncodingUTF_32},
{UTF_32BE, "UTF-32BE", &NkfEncodingUTF_32},
{UTF_32BE_BOM, "UTF-32BE-BOM", &NkfEncodingUTF_32},
{UTF_32LE, "UTF-32LE", &NkfEncodingUTF_32},
{UTF_32LE_BOM, "UTF-32LE-BOM", &NkfEncodingUTF_32},
{BINARY, "BINARY", &NkfEncodingASCII},
{-1, NULL, NULL}
}; };
static const struct { #define NKF_ENCODING_TABLE_SIZE 34
struct {
const char *name; const char *name;
const int id; const int id;
} encoding_name_to_id_table[] = { } encoding_name_to_id_table[] = {
@ -354,7 +384,7 @@ static const struct {
{"UTF-32LE", UTF_32LE}, {"UTF-32LE", UTF_32LE},
{"UTF-32LE-BOM", UTF_32LE_BOM}, {"UTF-32LE-BOM", UTF_32LE_BOM},
{"BINARY", BINARY}, {"BINARY", BINARY},
{"", -1} {NULL, -1}
}; };
#if defined(DEFAULT_CODE_JIS) #if defined(DEFAULT_CODE_JIS)
#define DEFAULT_ENCODING ISO_2022_JP #define DEFAULT_ENCODING ISO_2022_JP
@ -441,7 +471,7 @@ struct input_code{
}; };
static char *input_codename = NULL; /* NULL: unestablished, "": BINARY */ static char *input_codename = NULL; /* NULL: unestablished, "": BINARY */
static int output_encoding = DEFAULT_ENCODING; static nkf_encoding *output_encoding;
#if !defined(PERL_XS) && !defined(WIN32DLL) #if !defined(PERL_XS) && !defined(WIN32DLL)
static nkf_char noconvert(FILE *f); static nkf_char noconvert(FILE *f);
@ -451,9 +481,7 @@ static nkf_char kanji_convert(FILE *f);
static nkf_char h_conv(FILE *f,nkf_char c2,nkf_char c1); static nkf_char h_conv(FILE *f,nkf_char c2,nkf_char c1);
static nkf_char push_hold_buf(nkf_char c2); static nkf_char push_hold_buf(nkf_char c2);
static void set_iconv(nkf_char f, nkf_char (*iconv_func)(nkf_char c2,nkf_char c1,nkf_char c0)); static void set_iconv(nkf_char f, nkf_char (*iconv_func)(nkf_char c2,nkf_char c1,nkf_char c0));
static nkf_char s_iconv(nkf_char c2,nkf_char c1,nkf_char c0);
static nkf_char s2e_conv(nkf_char c2, nkf_char c1, nkf_char *p2, nkf_char *p1); static nkf_char s2e_conv(nkf_char c2, nkf_char c1, nkf_char *p2, nkf_char *p1);
static nkf_char e_iconv(nkf_char c2,nkf_char c1,nkf_char c0);
#if defined(UTF8_INPUT_ENABLE) || defined(UTF8_OUTPUT_ENABLE) #if defined(UTF8_INPUT_ENABLE) || defined(UTF8_OUTPUT_ENABLE)
/* UCS Mapping /* UCS Mapping
* 0: Shift_JIS, eucJP-ascii * 0: Shift_JIS, eucJP-ascii
@ -482,9 +510,6 @@ static void encode_fallback_perl(nkf_char c);
static void encode_fallback_subchar(nkf_char c); static void encode_fallback_subchar(nkf_char c);
static void (*encode_fallback)(nkf_char c) = NULL; static void (*encode_fallback)(nkf_char c) = NULL;
static nkf_char w2e_conv(nkf_char c2,nkf_char c1,nkf_char c0,nkf_char *p2,nkf_char *p1); static nkf_char w2e_conv(nkf_char c2,nkf_char c1,nkf_char c0,nkf_char *p2,nkf_char *p1);
static nkf_char w_iconv(nkf_char c2,nkf_char c1,nkf_char c0);
static nkf_char w_iconv16(nkf_char c2,nkf_char c1,nkf_char c0);
static nkf_char w_iconv32(nkf_char c2,nkf_char c1,nkf_char c0);
static nkf_char unicode_to_jis_common(nkf_char c2,nkf_char c1,nkf_char c0,nkf_char *p2,nkf_char *p1); static nkf_char unicode_to_jis_common(nkf_char c2,nkf_char c1,nkf_char c0,nkf_char *p2,nkf_char *p1);
static nkf_char w_iconv_common(nkf_char c1,nkf_char c0,const unsigned short *const *pp,nkf_char psize,nkf_char *p2,nkf_char *p1); static nkf_char w_iconv_common(nkf_char c1,nkf_char c0,const unsigned short *const *pp,nkf_char psize,nkf_char *p2,nkf_char *p1);
static void w16w_conv(nkf_char val, nkf_char *p2, nkf_char *p1, nkf_char *p0); static void w16w_conv(nkf_char val, nkf_char *p2, nkf_char *p1, nkf_char *p0);
@ -496,14 +521,8 @@ static void w_status(struct input_code *, nkf_char);
static int output_bom_f = FALSE; static int output_bom_f = FALSE;
static int output_endian = ENDIAN_BIG; static int output_endian = ENDIAN_BIG;
static nkf_char e2w_conv(nkf_char c2,nkf_char c1); static nkf_char e2w_conv(nkf_char c2,nkf_char c1);
static void w_oconv(nkf_char c2,nkf_char c1);
static void w_oconv16(nkf_char c2,nkf_char c1);
static void w_oconv32(nkf_char c2,nkf_char c1);
#endif #endif
static void e_oconv(nkf_char c2,nkf_char c1);
static nkf_char e2s_conv(nkf_char c2, nkf_char c1, nkf_char *p2, nkf_char *p1); static nkf_char e2s_conv(nkf_char c2, nkf_char c1, nkf_char *p2, nkf_char *p1);
static void s_oconv(nkf_char c2,nkf_char c1);
static void j_oconv(nkf_char c2,nkf_char c1);
static void fold_conv(nkf_char c2,nkf_char c1); static void fold_conv(nkf_char c2,nkf_char c1);
static void nl_conv(nkf_char c2,nkf_char c1); static void nl_conv(nkf_char c2,nkf_char c1);
static void z_conv(nkf_char c2,nkf_char c1); static void z_conv(nkf_char c2,nkf_char c1);
@ -895,6 +914,14 @@ static void nkf_str_upcase(const char *str, char *res, size_t length)
res[i] = 0; res[i] = 0;
} }
static nkf_encoding *nkf_enc_from_index(int idx)
{
if (idx < 0 || NKF_ENCODING_TABLE_SIZE <= idx) {
return 0;
}
return &nkf_encoding_table[idx];
}
static int nkf_enc_find_index(const char *name) static int nkf_enc_find_index(const char *name)
{ {
int i, index = -1; int i, index = -1;
@ -906,19 +933,17 @@ static int nkf_enc_find_index(const char *name)
return index; return index;
} }
#if defined(PERL_XS) || defined(WIN32DLL) static nkf_encoding *nkf_enc_find(const char *name)
static char* nkf_enc_name(const int index)
{ {
int i; int idx = -1;
const char* name = "ASCII"; idx = nkf_enc_find_index(name);
for (i = 0; encoding_id_to_name_table[i].id >= 0; i++) { if (idx < 0) return 0;
if (encoding_id_to_name_table[i].id == index) { return nkf_enc_from_index(idx);
return nkf_strcpy(encoding_id_to_name_table[i].name);
} }
}
return nkf_strcpy(name); #define nkf_enc_name(enc) (enc)->name
} #define nkf_enc_to_index(enc) (enc)->id
#endif #define nkf_enc_to_base_encoding(enc) (enc)->based_encoding
#ifdef WIN32DLL #ifdef WIN32DLL
#include "nkf32dll.c" #include "nkf32dll.c"
@ -1327,6 +1352,7 @@ void options(unsigned char *cp)
unsigned char *p; unsigned char *p;
unsigned char *cp_back = NULL; unsigned char *cp_back = NULL;
char codeset[32]; char codeset[32];
nkf_encoding *enc;
if (option_mode==1) if (option_mode==1)
return; return;
@ -1364,8 +1390,8 @@ void options(unsigned char *cp)
}else{ }else{
if (strcmp(long_option[i].name, "ic=") == 0){ if (strcmp(long_option[i].name, "ic=") == 0){
nkf_str_upcase(p, codeset, 32); nkf_str_upcase(p, codeset, 32);
i = nkf_enc_find_index(codeset); enc = nkf_enc_find(codeset);
switch (i) { switch (nkf_enc_to_index(enc)) {
case ISO_2022_JP: case ISO_2022_JP:
input_f = JIS_INPUT; input_f = JIS_INPUT;
break; break;
@ -1502,10 +1528,10 @@ void options(unsigned char *cp)
continue; continue;
} }
if (strcmp(long_option[i].name, "oc=") == 0){ if (strcmp(long_option[i].name, "oc=") == 0){
nkf_str_upcase(p, codeset, 32);
output_encoding = nkf_enc_find_index(codeset);
x0201_f = FALSE; x0201_f = FALSE;
switch (output_encoding) { nkf_str_upcase(p, codeset, 32);
output_encoding = nkf_enc_find(codeset);
switch (nkf_enc_to_index(output_encoding)) {
case ISO_2022_JP: case ISO_2022_JP:
output_conv = j_oconv; output_conv = j_oconv;
break; break;
@ -1880,16 +1906,16 @@ void options(unsigned char *cp)
case 'j': /* JIS output */ case 'j': /* JIS output */
case 'n': case 'n':
output_conv = j_oconv; output_conv = j_oconv;
output_encoding = ISO_2022_JP; output_encoding = nkf_enc_from_index(ISO_2022_JP);
continue; continue;
case 'e': /* AT&T EUC output */ case 'e': /* AT&T EUC output */
output_conv = e_oconv; output_conv = e_oconv;
cp932inv_f = FALSE; cp932inv_f = FALSE;
output_encoding = EUC_JP; output_encoding = nkf_enc_from_index(EUC_JP);
continue; continue;
case 's': /* SJIS output */ case 's': /* SJIS output */
output_conv = s_oconv; output_conv = s_oconv;
output_encoding = SHIFT_JIS; output_encoding = nkf_enc_from_index(SHIFT_JIS);
continue; continue;
case 'l': /* ISO8859 Latin-1 support, no conversion */ case 'l': /* ISO8859 Latin-1 support, no conversion */
iso8859_f = TRUE; /* Only compatible with ISO-2022-JP */ iso8859_f = TRUE; /* Only compatible with ISO-2022-JP */
@ -1937,21 +1963,22 @@ void options(unsigned char *cp)
output_conv = w_oconv; cp++; output_conv = w_oconv; cp++;
if (cp[0] == '0'){ if (cp[0] == '0'){
cp++; cp++;
output_encoding = UTF_8N; output_encoding = nkf_enc_from_index(UTF_8N);
} else { } else {
output_bom_f = TRUE; output_bom_f = TRUE;
output_encoding = UTF_8_BOM; output_encoding = nkf_enc_from_index(UTF_8_BOM);
} }
} else { } else {
int enc_idx;
if ('1'== cp[0] && '6'==cp[1]) { if ('1'== cp[0] && '6'==cp[1]) {
output_conv = w_oconv16; cp+=2; output_conv = w_oconv16; cp+=2;
output_encoding = UTF_16; enc_idx = UTF_16;
} else if ('3'== cp[0] && '2'==cp[1]) { } else if ('3'== cp[0] && '2'==cp[1]) {
output_conv = w_oconv32; cp+=2; output_conv = w_oconv32; cp+=2;
output_encoding = UTF_32; enc_idx = UTF_32;
} else { } else {
output_conv = w_oconv; output_conv = w_oconv;
output_encoding = UTF_8; output_encoding = nkf_enc_from_index(UTF_8);
continue; continue;
} }
if (cp[0]=='L') { if (cp[0]=='L') {
@ -1960,19 +1987,21 @@ void options(unsigned char *cp)
} else if (cp[0] == 'B') { } else if (cp[0] == 'B') {
cp++; cp++;
} else { } else {
output_encoding = nkf_enc_from_index(enc_idx);
continue; continue;
} }
if (cp[0] == '0'){ if (cp[0] == '0'){
cp++; cp++;
output_encoding = output_encoding == UTF_16 enc_idx = enc_idx == UTF_16
? (output_endian == ENDIAN_LITTLE ? UTF_16LE : UTF_16BE) ? (output_endian == ENDIAN_LITTLE ? UTF_16LE : UTF_16BE)
: (output_endian == ENDIAN_LITTLE ? UTF_32LE : UTF_32BE); : (output_endian == ENDIAN_LITTLE ? UTF_32LE : UTF_32BE);
} else { } else {
output_bom_f = TRUE; output_bom_f = TRUE;
output_encoding = output_encoding == UTF_16 enc_idx = enc_idx == UTF_16
? (output_endian == ENDIAN_LITTLE ? UTF_16LE_BOM : UTF_16BE_BOM) ? (output_endian == ENDIAN_LITTLE ? UTF_16LE_BOM : UTF_16BE_BOM)
: (output_endian == ENDIAN_LITTLE ? UTF_32LE_BOM : UTF_32BE_BOM); : (output_endian == ENDIAN_LITTLE ? UTF_32LE_BOM : UTF_32BE_BOM);
} }
output_encoding = nkf_enc_from_index(enc_idx);
} }
continue; continue;
#endif #endif
@ -3028,11 +3057,11 @@ nkf_char kanji_convert(FILE *f)
shift_mode = FALSE; shift_mode = FALSE;
NEXT; NEXT;
#endif /* X0212_ENABLE */ #endif /* X0212_ENABLE */
} else if (c1 == (JIS_X_0213_1&0x7F)){ } else if (c1 == 0x4F){
input_mode = JIS_X_0213_1; input_mode = JIS_X_0213_1;
shift_mode = FALSE; shift_mode = FALSE;
NEXT; NEXT;
} else if (c1 == (JIS_X_0213_2&0x7F)){ } else if (c1 == 0x50){
input_mode = JIS_X_0213_2; input_mode = JIS_X_0213_2;
shift_mode = FALSE; shift_mode = FALSE;
NEXT; NEXT;
@ -4469,7 +4498,7 @@ void j_oconv(nkf_char c2, nkf_char c1)
(*o_putc)(ESC); (*o_putc)(ESC);
(*o_putc)('$'); (*o_putc)('$');
(*o_putc)('('); (*o_putc)('(');
(*o_putc)(JIS_X_0213_2&0x7F); (*o_putc)(0x50);
} }
}else{ }else{
if(output_mode!=JIS_X_0212){ if(output_mode!=JIS_X_0212){
@ -4477,7 +4506,7 @@ void j_oconv(nkf_char c2, nkf_char c1)
(*o_putc)(ESC); (*o_putc)(ESC);
(*o_putc)('$'); (*o_putc)('$');
(*o_putc)('('); (*o_putc)('(');
(*o_putc)(JIS_X_0212&0x7F); (*o_putc)(0x44);
} }
} }
(*o_putc)(c2 & 0x7f); (*o_putc)(c2 & 0x7f);
@ -4515,7 +4544,7 @@ void j_oconv(nkf_char c2, nkf_char c1)
(*o_putc)(ESC); (*o_putc)(ESC);
(*o_putc)('$'); (*o_putc)('$');
(*o_putc)('('); (*o_putc)('(');
(*o_putc)(JIS_X_0213_1&0x7F); (*o_putc)(0x4F);
} }
}else if (output_mode != JIS_X_0208) { }else if (output_mode != JIS_X_0208) {
output_mode = JIS_X_0208; output_mode = JIS_X_0208;
@ -6317,7 +6346,7 @@ void reinit(void)
iconv_for_check = 0; iconv_for_check = 0;
#endif #endif
input_codename = NULL; input_codename = NULL;
output_encoding = DEFAULT_ENCODING; output_encoding = nkf_enc_from_index(DEFAULT_ENCODING);
#ifdef WIN32DLL #ifdef WIN32DLL
reinitdll(); reinitdll();
#endif /*WIN32DLL*/ #endif /*WIN32DLL*/

16
ext/nkf/nkf.c
View file

@ -64,7 +64,17 @@ rb_nkf_putchar(unsigned int c)
rb_encoding* rb_nkf_enc_get(const char *name) rb_encoding* rb_nkf_enc_get(const char *name)
{ {
int idx = rb_enc_find_index(name); int idx = rb_enc_find_index(name);
if (idx < 0) idx = rb_enc_replicate(name, rb_ascii_encoding()); if (idx < 0) {
nkf_encoding *nkf_enc = nkf_enc_find(name);
nkf_native_encoding * nkf_base_enc = nkf_enc_to_base_encoding(nkf_enc);
idx = rb_enc_find_index(nkf_enc_name(nkf_base_enc));
if (idx < 0) {
idx = rb_enc_replicate(name, rb_ascii_encoding());
} else {
rb_encoding *rb_enc = rb_enc_from_index(idx);
idx = rb_enc_replicate(name, rb_enc);
}
}
return rb_enc_from_index(idx); return rb_enc_from_index(idx);
} }
@ -475,11 +485,11 @@ Init_nkf()
rb_define_const(mNKF, "NOCONV", Qnil); rb_define_const(mNKF, "NOCONV", Qnil);
rb_define_const(mNKF, "UNKNOWN", Qnil); rb_define_const(mNKF, "UNKNOWN", Qnil);
rb_define_const(mNKF, "BINARY", rb_enc_from_encoding(rb_nkf_enc_get("BINARY"))); rb_define_const(mNKF, "BINARY", rb_enc_from_encoding(rb_nkf_enc_get("BINARY")));
rb_define_const(mNKF, "ASCII", rb_enc_from_encoding(rb_nkf_enc_get("US_ASCII"))); rb_define_const(mNKF, "ASCII", rb_enc_from_encoding(rb_nkf_enc_get("US-ASCII")));
rb_define_const(mNKF, "JIS", rb_enc_from_encoding(rb_nkf_enc_get("ISO-2022-JP"))); rb_define_const(mNKF, "JIS", rb_enc_from_encoding(rb_nkf_enc_get("ISO-2022-JP")));
rb_define_const(mNKF, "EUC", rb_enc_from_encoding(rb_nkf_enc_get("EUC-JP"))); rb_define_const(mNKF, "EUC", rb_enc_from_encoding(rb_nkf_enc_get("EUC-JP")));
rb_define_const(mNKF, "SJIS", rb_enc_from_encoding(rb_nkf_enc_get("Shift_JIS"))); rb_define_const(mNKF, "SJIS", rb_enc_from_encoding(rb_nkf_enc_get("Shift_JIS")));
rb_define_const(mNKF, "UTF8", rb_enc_from_encoding(rb_nkf_enc_get("UTF-8"))); rb_define_const(mNKF, "UTF8", rb_enc_from_encoding(rb_utf8_encoding()));
rb_define_const(mNKF, "UTF16", rb_enc_from_encoding(rb_nkf_enc_get("UTF-16"))); rb_define_const(mNKF, "UTF16", rb_enc_from_encoding(rb_nkf_enc_get("UTF-16")));
rb_define_const(mNKF, "UTF32", rb_enc_from_encoding(rb_nkf_enc_get("UTF-32"))); rb_define_const(mNKF, "UTF32", rb_enc_from_encoding(rb_nkf_enc_get("UTF-32")));